Qwen2.5-72B vs Qwen3.5 397B

Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.

Quick Verdict

Both models are tied with an overall score of 65.

Knowledge

Tie

Qwen2.5-72B

80.8

Qwen3.5 397B

80.8

83
MMLU
83
82
GPQA
82
80
SuperGPQA
80
78
OpenBookQA
78

Coding

Tie

Qwen2.5-72B

75

Qwen3.5 397B

75

75
HumanEval
75

Mathematics

Qwen2.5-72B

Qwen2.5-72B

83

Qwen3.5 397B

82

84
AIME 2023
83
86
AIME 2024
85
85
AIME 2025
84
80
HMMT Feb 2023
79
82
HMMT Feb 2024
81
81
HMMT Feb 2025
80
83
BRUMO 2025
82

Reasoning

Tie

Qwen2.5-72B

79

Qwen3.5 397B

79

80
SimpleQA
80
78
MuSR
78

Frequently Asked Questions

Which is better, Qwen2.5-72B or Qwen3.5 397B?

Qwen2.5-72B and Qwen3.5 397B are tied with identical overall scores of 65.

Which is better for knowledge tasks, Qwen2.5-72B or Qwen3.5 397B?

Qwen2.5-72B and Qwen3.5 397B are tied for knowledge tasks with average scores of 80.8.

Which is better for coding, Qwen2.5-72B or Qwen3.5 397B?

Qwen2.5-72B and Qwen3.5 397B are tied for coding with average scores of 75.

Which is better for math, Qwen2.5-72B or Qwen3.5 397B?

Qwen2.5-72B leads in math with an average score of 83 vs 82.

Which is better for reasoning, Qwen2.5-72B or Qwen3.5 397B?

Qwen2.5-72B and Qwen3.5 397B are tied for reasoning with average scores of 79.